| --- |
| library_name: kernels |
| license: apache-2.0 |
| tags: |
| - kernel |
| - webgpu |
| - wgsl |
| --- |
| # ai.onnx.LayerNormalization |
|
|
| `ai.onnx` · standard ONNX operator · ONNX opset ≥ 17 |
|
|
| ## Description |
|
|
| Normalizes a tensor along a suffix of axes starting at `axis` by subtracting the mean and dividing by the square root of the variance plus `epsilon`, then scales and optionally shifts the result with learnable `Scale` and `B` tensors. The output `Y` has the same shape as `X`; optional outputs `Mean` and `InvStdDev` expose the per-normalization-group statistics computed during normalization. |
|
|
| See the [ONNX `LayerNormalization` spec](https://onnx.ai/onnx/operators/onnx__LayerNormalization.html) for the reference semantics. |
|
|
| ## Inputs |
|
|
| | Name | Upstream name | Logical dtype | Rank | Shape | Description | Presence | |
| | --- | --- | --- | --- | --- | --- | --- | |
| | `x` | `X` | `T` | — | — | Tensor to be normalized. | required | |
| | `scale` | `Scale` | `T` | — | — | Scale tensor applied after normalization. | required | |
| | `b` | `B` | `T` | — | — | Optional bias tensor added after scaling. | optional | |
|
|
| ## Outputs |
|
|
| | Name | Upstream name | Logical dtype | Rank | Shape | Description | Presence | |
| | --- | --- | --- | --- | --- | --- | --- | |
| | `y` | `Y` | `T` | same as `x` | same as `x` | Normalized and scaled output tensor; same shape as X. | required | |
| | `mean` | `Mean` | `float32` | same as `x` | — | Per-normalization-group mean in the ONNX broadcastable keepdims shape: dimensions before `axis` are preserved and dimensions from `axis` onward are 1. | optional | |
| | `invStdDev` | `InvStdDev` | `float32` | same as `x` | — | Per-normalization-group reciprocal standard deviation `1 / sqrt(variance + epsilon)`, returned in the same ONNX broadcastable keepdims shape as `Mean`. | optional | |
|
|
| ## Attributes |
|
|
| Default values (overridable per request): |
|
|
| | Attribute | Default | Description | |
| | --- | --- | --- | |
| | `axis` | `-1` | The first axis of the normalization range; all axes from `axis` to the last are normalized together. Negative values count from the end; the default `-1` normalizes only the last dimension. | |
| | `epsilon` | `0.00001` | Small constant added to the variance before taking the square root to avoid division by zero. | |
| | `stash_type` | `1` | TensorProto element type used for the normalization stage and optional statistics; the implemented ONNX route supports the standard float32 value (`1`). | |
|
|
| ## Type constraints |
|
|
| | Variable | Allowed dtypes | |
| | --- | --- | |
| | `T` | `float32`, `float16` | |
|
|
| ## Files |
|
|
| - [`metadata.json`](build/webgpu/metadata.json) — kernel metadata (id, digests, per-variant templates, provenance) |
| - [`manifest.json`](build/webgpu/manifest.json) — the op contract (source of truth) |
| - [`test.json`](build/webgpu/test.json) — correctness cases |
| - [`bench.json`](build/webgpu/bench.json) — benchmark + tuning cases |
| - [`layer-normalization.wgsl.jinja`](build/webgpu/layer-normalization.wgsl.jinja) |
| - [`norm-row-stats.wgsl.jinja`](build/webgpu/norm-row-stats.wgsl.jinja) |
|
|
| ## Use with `@huggingface/kernels` |
|
|
| ```sh |
| npm install --save-exact @huggingface/kernels@0.0.1-preview.2 |
| ``` |
|
|
| Required output shapes and logical data types are inferred from the supplied inputs and attributes; result tensors are allocated automatically. |
|
|
| The `version: 1` option selects the published kernel contract; it is independent of any operator opset, contrib `since_version`, or model version. |
| It follows the `v1` branch as fixes land. To pin exact artifact bytes, pass a 40-character commit `revision` instead of `version`. |
|
|
| Replace each `*Data` placeholder with a typed array containing the corresponding input data. |
|
|
| ```js |
| import { getKernel } from "@huggingface/kernels"; |
| |
| const kernel = await getKernel("webgpu-kernels/ai.onnx.LayerNormalization", { version: 1 }); |
| const { y } = await kernel({ |
| x: { data: xData, shape: [1, 4] }, |
| scale: { data: scaleData, shape: [4] }, |
| }); |
| ``` |
|
|
